run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 19:30:01 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Issue with LlamaParse - Something went wrong while extracting the markdown. #476

New Issue
Open
opened 2026-02-16 00:17:57 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 00:17:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @vicam001 on GitHub (May 20, 2025).

Describe the bug
We use LlamaParse to extract the information from the HTML of an email.
We have been using for over a month without any issue.
Today, we are starting to get the error below:

Something went wrong while extracting the markdown.

We also get it with files that previously were successfully parsed, until yesterday it was working fine.

Image

Files
If possible, please provide the PDF file causing the issue.

Job ID

There are multiple, I share the ID of the First job that has failed: df976d43-96b4-4c78-9564-f2685458b03e

Client:

  • API
  • Frontend (cloud.llamaindex.ai)

Additional context
Add any additional context about the problem here.
What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc.
Screenshots, code snippets, etc.

Originally created by @vicam001 on GitHub (May 20, 2025). **Describe the bug** We use LlamaParse to extract the information from the HTML of an email. We have been using for over a month without any issue. Today, we are starting to get the error below: _Something went wrong while extracting the markdown._ We also get it with files that previously were successfully parsed, until yesterday it was working fine. <img width="653" alt="Image" src="https://github.com/user-attachments/assets/42e936d9-5041-4511-9f32-bfab0d3cdd03" /> **Files** If possible, please provide the PDF file causing the issue. **Job ID** There are multiple, I share the ID of the First job that has failed: df976d43-96b4-4c78-9564-f2685458b03e **Client:** - API - Frontend (cloud.llamaindex.ai) **Additional context** Add any additional context about the problem here. What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc. Screenshots, code snippets, etc.
yindo added the bug label 2026-02-16 00:17:57 -05:00
yindo commented 2026-02-16 00:17:57 -05:00
Author
Owner
Copy Link
Copy Source

@sophie-aistribute commented on GitHub (May 28, 2025):

Having similar issue here and it has never occured before.

When using Parse with Agent mode, even the job succeed, the markdown result is missing content (although the text do get extracted).

This appears to be happened randomly. Switching the model would sometimes solve the problem.

parser = LlamaParse(
  parse_mode="parse_page_with_agent"
  invalidate_cache=True
  do_not_cache=True
  model="anthropic-sonnet-3.5" // sometimes switching to gemini-2.5-pro helps, but often gemini-2.5-pro also fails
  output_tables_as_HTML=False // doesn't matter if this flag is true or false
  take_screenshot=True
  disable_ocr=False
  disable_image_extraction=True // doesn't matter if this flag is true or false
)

Job ID:
3a7075be-b6d7-46c1-a7c7-75dbfdbeae0a
d5c3fe4e-b3b5-44c4-8b5c-2edb8a206c57
81c807e7-3783-484d-b4a2-6c4851344bc8

These jobs all runs on the same file. The markdown result on page 4 is incorrect.

@sophie-aistribute commented on GitHub (May 28, 2025): Having similar issue here and it has never occured before. When using `Parse with Agent` mode, even the job succeed, the markdown result is missing content (although the text do get extracted). This appears to be happened randomly. Switching the model would sometimes solve the problem. ``` parser = LlamaParse( parse_mode="parse_page_with_agent" invalidate_cache=True do_not_cache=True model="anthropic-sonnet-3.5" // sometimes switching to gemini-2.5-pro helps, but often gemini-2.5-pro also fails output_tables_as_HTML=False // doesn't matter if this flag is true or false take_screenshot=True disable_ocr=False disable_image_extraction=True // doesn't matter if this flag is true or false ) ``` Job ID: 3a7075be-b6d7-46c1-a7c7-75dbfdbeae0a d5c3fe4e-b3b5-44c4-8b5c-2edb8a206c57 81c807e7-3783-484d-b4a2-6c4851344bc8 These jobs all runs on the same file. The markdown result on page 4 is incorrect.
yindo commented 2026-02-16 00:17:58 -05:00
Author
Owner
Copy Link
Copy Source

@cholley6 commented on GitHub (May 29, 2025):

We are also having issues with Markdown from PDFs. The issue only happens in Balanced mode, in premium mode it runs fine.

Error Code: DOCUMENT_PIPELINE_ERROR
Error Message: MARKDOWN_EXTRACTION_FAILED

Faield JobIDs:
e6a7b5d4-4e14-4a47-bc8a-0f108008c4f5
e8881cda-58b9-4451-9d00-c388d13b07a0
6cbede4a-c3c3-476a-982f-954891507747

Successful Premium Mode JobID for same doc:
443c0106-9235-4d48-b687-3d89e84922f7

@cholley6 commented on GitHub (May 29, 2025): We are also having issues with Markdown from PDFs. The issue only happens in Balanced mode, in premium mode it runs fine. Error Code: DOCUMENT_PIPELINE_ERROR Error Message: MARKDOWN_EXTRACTION_FAILED Faield JobIDs: e6a7b5d4-4e14-4a47-bc8a-0f108008c4f5 e8881cda-58b9-4451-9d00-c388d13b07a0 6cbede4a-c3c3-476a-982f-954891507747 Successful Premium Mode JobID for same doc: 443c0106-9235-4d48-b687-3d89e84922f7
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#476
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?